Wealth & Retirement · 121 skills
- Retirement income & withdrawal strategy
- Tax: Roth/RRSP, loss harvesting, rule changes
- Estate, insurance & cross-border planning
- Advisor tools: meeting prep, compliance pre-screen
Agent Library
21,500+ skills & agents. Every one governed.
5,814 pre-built agents and 15,654 library skills across 24 industries and 12 roles per industry — installable from the catalog, connected to your systems, and run through the same fail-closed gate chain as everything else on Cortex.
21,511 governed library items · counted live from the catalog, not a marketing number
Agent Studio
skills
Search KBCreate ticketSend email add
Publishedv4 · reliability 96
Where is order #4471?
Shipped, arriving Thursday.tools: Search KB · $0.004
studio ▸ build → publish → chat-test
Collections
Start from a curated collection.
Hand-built suites for the jobs enterprises automate first — every collection ships governed, with policies and audit built in.
Enterprise Role Packs · 11 roles
- Service, Sales & Customer Success
- IT Service Desk, HR & Finance Ops
- Legal Intake, Procurement & Field Ops
- Risk & Compliance
Productivity Pack · 9 agents
- Inbox triage & email drafting
- Meeting prep, notes & follow-up
- Smart scheduling & daily brief
- Executive assistant orchestration
Gene collection · 630 agents
- Smart claims, actuarial & AML
- Audit, GRC & ESG reporting
- ITAM / ITSM & security operations
- Data & analytics workbenches
Browse the library
Find the skill your team needs.
Search 21,500+ governed skills and agents, or filter by industry and type — every result installs from the catalog and runs through the same gates.
All industriesInsuranceBanking & Capital MarketsHealthcare & Hospital AdminLegal ServicesIT Service ManagementHuman ResourcesFinance & AccountingSalesMarketingCustomer SupportSupply Chain & LogisticsManufacturingRetail & E-commerceReal EstateEducationGovernment & Public SectorEnergy & UtilitiesTelecommunicationsPharmaceutical & Life SciencesHospitality & TravelConstruction & EngineeringAutomotiveCybersecurityProfessional Services
21,386 results
Watchlist Screening
Screen entities against consolidated watchlists including OFAC SDN, EU sanctions, UN consolidated list, and domestic law enforcement databases. Supports batch and real-time modes.
Create Webhook Endpoint
Set up incoming webhook endpoints with payload validation, transformation, and routing to internal workflows.
Create Automated Workflow
Design and deploy an automated multi-step workflow with triggers (schedule, event, API), conditional branching, approvals, and notifications.
Create Audit Workpaper
Auto-generate structured audit workpapers from testing procedures. Pre-populates with objectives, scope, methodology, sample details, and findings templates.
Explain Model Decision
Generate explainable AI analysis for a model prediction. Produces SHAP values, LIME explanations, counterfactuals, and plain-English narratives.
Zero Trust Maturity Assessment
Evaluate zero trust architecture maturity across 5 pillars -- identity, device, network, application, and data with maturity scoring and roadmap generation.
Inbox Review Agent
Summarizes supplied email text, assesses potential priority, and drafts a handling recommendation; it does not read or route a mailbox.
Email Drafting Agent
Searches approved knowledge and drafts email copy from supplied context; sending remains outside this template.
Meeting Prep Agent
Turns supplied meeting context into a concise pre-read; it does not read calendars, CRM records, or message threads automatically.
Meeting Notes Agent
Summarizes a supplied transcript and drafts structured notes; it does not create tasks or distribute notes.
Follow-up Drafting Agent
Summarizes supplied commitment context and drafts a follow-up; it does not track replies, send nudges, or schedule reminders.
Scheduling Draft Agent
Drafts scheduling language from availability supplied in the request; it does not read or write calendars.
On-demand Brief Agent
Runs a governed read query and summarizes supplied results into an on-demand brief; it does not aggregate personal apps or deliver on a schedule.
Research Assistant Agent
Searches approved Cortex knowledge, summarizes supplied findings, and drafts a research brief; it does not browse the public web.
Executive Briefing Agent
Searches approved knowledge and turns supplied context into an executive brief; it does not delegate agents or manage a calendar or inbox.
Service Agent
Searches approved support knowledge and drafts a response or escalation recommendation; it does not update tickets.
Sales Agent
Prepares CRM enrichment analysis, recommends a next action, and drafts follow-up copy; it does not update CRM records.
Ecommerce Agent
Looks up a supplied order record, searches approved product knowledge, and drafts a response; it does not issue refunds.
Customer Success Agent
Summarizes supplied account context, assesses potential risk, and drafts outreach; it does not monitor accounts or send messages.
IT Service Desk Agent
Triages supplied incident context, searches approved guidance, and drafts a response; it does not run remediation or provision access.
HR Agent
Searches approved HR knowledge, summarizes supplied context, and drafts a policy-grounded response; it does not create or route cases.
Finance Operations Agent
Looks up supplied records, runs governed read queries, and drafts a finance-operations brief; it does not post adjustments or route exceptions.
Legal Intake Agent
Summarizes supplied legal context, checks a proposed response against policy, and drafts an intake brief; it does not create or route matters.
Procurement Agent
Looks up supplied records, searches approved procurement knowledge, and drafts a request brief; it does not approve purchases.
Governed by default
Install is the easy part. Governance comes with it.
Library agents aren't scripts — they're governed identities. Installing one registers it with an owner, a budget, allowed models and actions, and a place in the audit ledger.
Choose from the catalog
Filter by your industry and role; every item lists the systems it connects to and the skills it invokes.
Wire it to your stack
Connectors, MCP servers, and OpenAPI imports — scoped by allowlists and DLP at the gateway.
Every run through the gates
Identity, budget, guardrails, registry, control tower, execute, output guard — then a signed receipt in the Trust Ledger. On every plan.
Don't see the skill you need?
The visual skill builder ships new skills without code — or tell us what's missing and we'll point you at the closest governed pattern.